AI-Enhanced Non-Intrusive Load Monitoring for Smart Home Energy Optimization and User-Centric Interaction
Non-Intrusive Load Monitoring (NILM) technology, enabled by high-precision electrical data acquisition sensors at household entry points, facilitates real-time monitoring of electricity consumption, enhancing user interaction with smart home systems and reducing electrical safety risks. However, the...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Informatics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9709/12/2/55 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839653755063107584 |
|---|---|
| author | Xiang Li Yunhe Chen Xinyu Jia Fan Shen Bowen Sun Shuqing He Jia Guo |
| author_facet | Xiang Li Yunhe Chen Xinyu Jia Fan Shen Bowen Sun Shuqing He Jia Guo |
| author_sort | Xiang Li |
| collection | DOAJ |
| description | Non-Intrusive Load Monitoring (NILM) technology, enabled by high-precision electrical data acquisition sensors at household entry points, facilitates real-time monitoring of electricity consumption, enhancing user interaction with smart home systems and reducing electrical safety risks. However, the growing diversity of household appliances and limitations in NILM accuracy and robustness necessitate innovative solutions. Additionally, outdated public datasets fail to capture the rapid evolution of modern appliances. To address these challenges, we constructed a high-sampling-rate voltage–current dataset, measuring 15 common household appliances across diverse scenarios in a controlled laboratory environment tailored to regional grid standards (220 V/50 Hz). We propose an AI-driven NILM method that integrates power-mapped, color-coded voltage–current (V–I) trajectories with frequency-domain features to significantly improve load recognition accuracy and robustness. By leveraging deep learning frameworks, this approach enriches temporal feature representation through chromatic mapping of instantaneous power and incorporates frequency-domain spectrograms to capture dynamic load behaviors. A novel channel-wise attention mechanism optimizes multi-dimensional feature fusion, dynamically prioritizing critical information while suppressing noise. Comparative experiments on the custom dataset demonstrate superior performance, particularly in distinguishing appliances with similar load profiles, underscoring the method’s potential for advancing smart home energy management, user-centric energy feedback, and social informatics applications in complex electrical environments. |
| format | Article |
| id | doaj-art-2bbbb3f9cc484738913737059d4ffb51 |
| institution | Matheson Library |
| issn | 2227-9709 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Informatics |
| spelling | doaj-art-2bbbb3f9cc484738913737059d4ffb512025-06-25T13:57:24ZengMDPI AGInformatics2227-97092025-06-011225510.3390/informatics12020055AI-Enhanced Non-Intrusive Load Monitoring for Smart Home Energy Optimization and User-Centric InteractionXiang Li0Yunhe Chen1Xinyu Jia2Fan Shen3Bowen Sun4Shuqing He5Jia Guo6College of Politics and Public Administration, Tianjin Normal University, Tianjin 300387, ChinaCollege of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, ChinaCollege of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, ChinaCollege of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, ChinaCollege of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, ChinaSchool of Information Science and Engineering, Linyi University, Linyi 276000, ChinaCollege of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, ChinaNon-Intrusive Load Monitoring (NILM) technology, enabled by high-precision electrical data acquisition sensors at household entry points, facilitates real-time monitoring of electricity consumption, enhancing user interaction with smart home systems and reducing electrical safety risks. However, the growing diversity of household appliances and limitations in NILM accuracy and robustness necessitate innovative solutions. Additionally, outdated public datasets fail to capture the rapid evolution of modern appliances. To address these challenges, we constructed a high-sampling-rate voltage–current dataset, measuring 15 common household appliances across diverse scenarios in a controlled laboratory environment tailored to regional grid standards (220 V/50 Hz). We propose an AI-driven NILM method that integrates power-mapped, color-coded voltage–current (V–I) trajectories with frequency-domain features to significantly improve load recognition accuracy and robustness. By leveraging deep learning frameworks, this approach enriches temporal feature representation through chromatic mapping of instantaneous power and incorporates frequency-domain spectrograms to capture dynamic load behaviors. A novel channel-wise attention mechanism optimizes multi-dimensional feature fusion, dynamically prioritizing critical information while suppressing noise. Comparative experiments on the custom dataset demonstrate superior performance, particularly in distinguishing appliances with similar load profiles, underscoring the method’s potential for advancing smart home energy management, user-centric energy feedback, and social informatics applications in complex electrical environments.https://www.mdpi.com/2227-9709/12/2/55enhancing user interactionnon-intrusive load monitoring (NILM)artificial intelligencevoltage–current trajectory analysisfrequency-domain analysisload classification |
| spellingShingle | Xiang Li Yunhe Chen Xinyu Jia Fan Shen Bowen Sun Shuqing He Jia Guo AI-Enhanced Non-Intrusive Load Monitoring for Smart Home Energy Optimization and User-Centric Interaction Informatics enhancing user interaction non-intrusive load monitoring (NILM) artificial intelligence voltage–current trajectory analysis frequency-domain analysis load classification |
| title | AI-Enhanced Non-Intrusive Load Monitoring for Smart Home Energy Optimization and User-Centric Interaction |
| title_full | AI-Enhanced Non-Intrusive Load Monitoring for Smart Home Energy Optimization and User-Centric Interaction |
| title_fullStr | AI-Enhanced Non-Intrusive Load Monitoring for Smart Home Energy Optimization and User-Centric Interaction |
| title_full_unstemmed | AI-Enhanced Non-Intrusive Load Monitoring for Smart Home Energy Optimization and User-Centric Interaction |
| title_short | AI-Enhanced Non-Intrusive Load Monitoring for Smart Home Energy Optimization and User-Centric Interaction |
| title_sort | ai enhanced non intrusive load monitoring for smart home energy optimization and user centric interaction |
| topic | enhancing user interaction non-intrusive load monitoring (NILM) artificial intelligence voltage–current trajectory analysis frequency-domain analysis load classification |
| url | https://www.mdpi.com/2227-9709/12/2/55 |
| work_keys_str_mv | AT xiangli aienhancednonintrusiveloadmonitoringforsmarthomeenergyoptimizationandusercentricinteraction AT yunhechen aienhancednonintrusiveloadmonitoringforsmarthomeenergyoptimizationandusercentricinteraction AT xinyujia aienhancednonintrusiveloadmonitoringforsmarthomeenergyoptimizationandusercentricinteraction AT fanshen aienhancednonintrusiveloadmonitoringforsmarthomeenergyoptimizationandusercentricinteraction AT bowensun aienhancednonintrusiveloadmonitoringforsmarthomeenergyoptimizationandusercentricinteraction AT shuqinghe aienhancednonintrusiveloadmonitoringforsmarthomeenergyoptimizationandusercentricinteraction AT jiaguo aienhancednonintrusiveloadmonitoringforsmarthomeenergyoptimizationandusercentricinteraction |